Prometheus之主机告警rules配置

prometheus.yml

# my global config
global:
  scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
  # scrape_timeout is set to the global default (10s).

# Alertmanager configuration
alerting:
  alertmanagers:
    - static_configs:
        - targets:
           - 10.0.9.15:9093

# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
  # - "first_rules.yml"
  # - "second_rules.yml"
  - "rules/*.yaml"
  - "alert_rules/*.yaml"


# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
  - job_name: "prometheus"

    # metrics_path defaults to '/metrics'
    # scheme defaults to 'http'.

    static_configs:
      - targets: ["localhost:9090"]

  - job_name: "node"
    static_configs:
      - targets: ["localhost:9100"]
        labels:
          appname: "prometheus-01"

hosts.yaml

 /usr/local/prometheus/rules/hosts.yaml

groups:
- name: Host
  rules:
  - alert: HostMemory Usage
    expr: (node_memory_MemTotal_bytes - (node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes)) / node_memory_MemTotal_bytes * 100 >  90
    for: 1m
    labels:
      name: Memory
      severity: Warning
    annotations:
      summary: " {{ $labels.appname }} "
      description: "宿主机内存使用率超过90%."
      value: "{{ $value }}%"
  - alert: HostCPU Usage
    expr: sum(avg without (cpu)(irate(node_cpu_seconds_total{mode!='idle'}[5m]))) by (instance,appname) > 0.8
    for: 1m
    labels:
      name: CPU
      severity: Warning
    annotations:
      summary: " {{ $labels.appname }} "
      description: "宿主机CPU使用率超过80%."
      value: "{{ $value }}%"
  - alert: HostLoad
    expr: node_load5 > 20
    for: 1m
    labels:
      name: Load
      severity: Warning
    annotations:
      summary: "{{ $labels.appname }} "
      description: " 主机负载5分钟超过20."
      value: "{{ $value }}"
  - alert: HostFilesystem Usage
    expr: (node_filesystem_size_bytes-node_filesystem_free_bytes)/node_filesystem_size_bytes*100>80
    for: 1m
    labels:
      name: Disk
      severity: Warning
    annotations:
      summary: " {{ $labels.appname }} "
      description: " 宿主机 [ {{ $labels.mountpoint }} ]分区使用超过80%."
      value: "{{ $value }}%"
  - alert: HostDiskio writes
    expr: irate(node_disk_writes_completed_total{job=~"Host"}[1m]) > 10
    for: 1m
    labels:
      name: Diskio
      severity: Warning
    annotations:
      summary: " {{ $labels.appname }} "
      description: " 宿主机 [{{ $labels.device }}]磁盘1分钟平均写入IO负载较高."
      value: "{{ $value }}iops"
  - alert: HostDiskio reads
    expr: irate(node_disk_reads_completed_total{job=~"Host"}[1m]) > 10
    for: 1m
    labels:
      name: Diskio
      severity: Warning
    annotations:
      summary: " {{ $labels.appname }} "
      description: " 宿主机 [{{ $labels.device }}]磁盘1分钟平均读取IO负载较高."
      value: "{{ $value }}iops"
  - alert: HostNetwork_receive
    expr: irate(node_network_receive_bytes_total{device!~"lo|bond[0-9]|cbr[0-9]|veth.*|virbr.*|ovs-system"}[5m]) / 1048576  > 10
    for: 1m
    labels:
      name: Network_receive
      severity: Warning
    annotations:
      summary: " {{ $labels.appname }} "
      description: " 宿主机 [{{ $labels.device }}] 网卡5分钟平均接收流量超过10Mbps."
      value: "{{ $value }}3Mbps"
  - alert: hostNetwork_transmit
    expr: irate(node_network_transmit_bytes_total{device!~"lo|bond[0-9]|cbr[0-9]|veth.*|virbr.*|ovs-system"}[5m]) / 1048576  > 10
    for: 1m
    labels:
      name: Network_transmit
      severity: Warning
    annotations:
      summary: " {{ $labels.appname }} "
      description: " 宿主机 [{{ $labels.device }}] 网卡5分钟内平均发送流量超过10Mbps."
      value: "{{ $value }}10Mbps"

告警实例